{"id":"https://openalex.org/W7128684160","doi":"https://doi.org/10.48550/arxiv.2602.10532","title":"Statistical Inference and Learning for Shapley Additive Explanations (SHAP)","display_name":"Statistical Inference and Learning for Shapley Additive Explanations (SHAP)","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128684160","doi":"https://doi.org/10.48550/arxiv.2602.10532"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.10532","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084656873","display_name":"Justin Whitehouse","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Whitehouse, Justin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067698930","display_name":"Ayush Sawarni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sawarni, Ayush","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125696883","display_name":"Vasilis Syrgkanis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Syrgkanis, Vasilis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084656873"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.897599995136261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.897599995136261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.015399999916553497,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.012799999676644802,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7325000166893005},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.54339998960495},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.5335000157356262},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.484499990940094},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.45410001277923584},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44369998574256897}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7325000166893005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6284000277519226},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.45980000495910645},{"id":"https://openalex.org/C199022921","wikidata":"https://www.wikidata.org/wiki/Q240046","display_name":"Shapley value","level":3,"score":0.45410001277923584},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C203223496","wikidata":"https://www.wikidata.org/wiki/Q4681344","display_name":"Additive model","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.3052000105381012},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C194531419","wikidata":"https://www.wikidata.org/wiki/Q17104825","display_name":"Nuisance parameter","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C194648359","wikidata":"https://www.wikidata.org/wiki/Q3318054","display_name":"Generalized additive model","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.10532","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.10532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.10532","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,82],"SHAP":[1,24,59,101,149,264],"(short":[2],"for":[3,13,86,115,130,190,217,241,275],"Shapley":[4,29,140],"additive":[5,141],"explanation)":[6],"framework":[7],"has":[8],"become":[9],"an":[10,51],"essential":[11],"tool":[12],"attributing":[14],"importance":[15,71],"to":[16,35,39,50,74,95,226,238,261],"variables":[17],"in":[18,42,72,133,236],"predictive":[19],"tasks.":[20],"In":[21,122,221],"model-agnostic":[22],"settings,":[23],"uses":[25],"the":[26,40,55,98,136,148,169,205,229,233,242,263],"concept":[27],"of":[28,69,135,139,168,172,192,232],"values":[30],"from":[31,159],"cooperative":[32],"game":[33],"theory":[34],"fairly":[36],"allocate":[37],"credit":[38],"features":[41],"a":[43,127,152,180,218,253],"vector":[44],"$X$":[45],"based":[46],"on":[47,119],"their":[48,108],"contribution":[49],"outcome":[52],"$Y$.":[53],"While":[54],"explanations":[56,90],"offered":[57],"by":[58,62,146,251],"are":[60],"local":[61,89],"nature,":[63],"learners":[64],"often":[65],"need":[66],"global":[67,92],"measures":[68],"feature":[70,80],"order":[73,237],"improve":[75],"model":[76],"explainability":[77],"and":[78,270],"perform":[79],"selection.":[81],"most":[83],"common":[84],"approach":[85,129],"converting":[87],"these":[88,120,249],"into":[91],"ones":[93],"is":[94,195,209],"compute":[96],"either":[97],"mean":[99,103],"absolute":[100],"or":[102],"squared":[104],"SHAP.":[105,173],"However,":[106],"despite":[107],"ubiquity,":[109],"there":[110],"do":[111],"not":[112,210],"exist":[113],"approaches":[114],"performing":[116],"statistical":[117],"inference":[118,240],"quantities.":[121],"this":[123],"paper,":[124],"we":[125,178,213,223],"take":[126],"semi-parametric":[128],"calibrating":[131],"confidence":[132],"estimates":[134,167],"$p$th":[137,170,245],"powers":[138,171],"explanations.":[142],"We":[143,247],"show":[144,179,224],"that,":[145],"treating":[147],"curve":[150,265],"as":[151],"nuisance":[153],"function":[154,235,278],"that":[155,183,257],"must":[156],"be":[157,259],"estimated":[158],"data,":[160],"one":[161],"can":[162,258],"reliably":[163],"construct":[164,214],"asymptotically":[165,196],"normal":[166],"When":[174,198],"$p":[175],"\\geq":[176],"2$,":[177],"de-biased":[181,215],"estimator":[182],"combines":[184],"U-statistics":[185,216],"with":[186],"Neyman":[187,254],"orthogonal":[188,255],"scores":[189],"functionals":[191],"nested":[193],"regressions":[194],"normal.":[197],"$1":[199],"\\leq":[200],"p":[201],"<":[202],"2$":[203],"(and":[204],"hence":[206],"target":[207],"parameter":[208,231],"twice":[211],"differentiable),":[212],"smoothed":[219],"alternative.":[220],"particular,":[222],"how":[225],"carefully":[227],"tune":[228],"temperature":[230],"smoothing":[234],"obtain":[239],"true,":[243],"unsmoothed":[244],"power.":[246],"complement":[248],"results":[250],"presenting":[252],"loss":[256],"used":[260,277],"learn":[262],"via":[266],"empirical":[267],"risk":[268,273],"minimization":[269],"discussing":[271],"excess":[272],"guarantees":[274],"commonly":[276],"classes.":[279]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-13T00:00:00"}